input vcf

inputs

 {
   "{{ project_name }}.benchmarking_dir": "oss://pgx-result/renluyao/manuscript_v3.0/reference_dataset_v4.0/",
-  "{{ project_name }}.SENTIEON_INSTALL_DIR": "/opt/sentieon-genomics",
   "{{ project_name }}.fasta": "GRCh38.d1.vd1.fa",
   "{{ project_name }}.BENCHMARKdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/rtg-hap:latest",
-  "{{ project_name }}.gvcf": {{ gvcf_list.split(";") | tojson }},
-  "{{ project_name }}.gvcf_idx": {{ gvcf_idx_list.split(";") | tojson }},
+  "{{ project_name }}.LCL8": "{{ LCL8 }}",
   "{{ project_name }}.disk_size": "500",
+  "{{ project_name }}.LCL5": "{{ LCL5 }}",
+  "{{ project_name }}.rename": "{{ rename }}",
   "{{ project_name }}.project": "{{ project }}",
   "{{ project_name }}.SMALLcluster_config": "OnDemand bcs.ps.g.xlarge img-ubuntu-vpc",
   "{{ project_name }}.BIGcluster_config": "OnDemand bcs.a2.7xlarge img-ubuntu-vpc",
-  "{{ project_name }}.SENTIEONdocker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/sentieon-genomics:v2018.08.01",
+  "{{ project_name }}.LCL6": "{{ LCL6 }}",
   "{{ project_name }}.MENDELIANdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/vbt:v1.1",
+  "{{ project_name }}.LCL7": "{{ LCL7 }}",
   "{{ project_name }}.DIYdocker": "registry-vpc.cn-shanghai.aliyuncs.com/pgx-docker-registry/high_confidence_call_manuscript:v1.4",
   "{{ project_name }}.ref_dir": "oss://pgx-reference-data/GRCh38.d1.vd1/"
-}
+}

tasks/benchmark.wdl

 	File vcf
 	File benchmarking_dir
 	File ref_dir
-	String sample = basename(vcf,".splited.vcf")
+	String sample = basename(vcf,".vcf")
 	String fasta
 	String docker
 	String cluster_config
 
 		export HGREF=/cromwell_root/tmp/reference_data/GRCh38.d1.vd1.fa
 
-		cat ${vcf} | grep '#' > header
-		cat ${vcf} | grep -v '#' | grep -v '0/0' | grep -v '\./\.'| awk '
-		    BEGIN { OFS = "\t" }
-		     { 
-		        for ( i=9; i<=NF; i++ ) { 
-		            split($i,a,":") ;$i = a[1];
-		        } 
-		    } 
-		    { print }
-		' > body
-		cat header body > filtered.vcf
-
-		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip filtered.vcf -c > ${sample}.rtg.vcf.gz
+		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip ${vcf} -c > ${sample}.rtg.vcf.gz
 		/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.rtg.vcf.gz
 
 		if [[ ${sample} =~ "LCL5" ]];then

tasks/merge_family.wdl

  task merge_family {
-	Array[File] splited_vcf
+	File LCL5_vcf_gz
+	File LCL5_vcf_idx
+	File LCL6_vcf_gz
+	File LCL6_vcf_idx
+	File LCL7_vcf_gz
+	File LCL7_vcf_idx
+	File LCL8_vcf_gz
+	File LCL8_vcf_idx
+	File rename
 	String project
 	String docker
 	String cluster_config
 	String disk_size
 	
 	command <<<
+		opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfannotate --relabel=${rename} -i ${LCL5_vcf_gz} -o LCL5.vcf.gz
 
-		mkdir -p /cromwell_root/tmp/vcf
-
-		cp ${sep=" " splited_vcf} /cromwell_root/tmp/vcf
-
-		for a in /cromwell_root/tmp/vcf/*vcf
-		do
-			for b in /cromwell_root/tmp/vcf/*vcf
-			do
-				for c in /cromwell_root/tmp/vcf/*vcf
-				do
-					for d in /cromwell_root/tmp/vcf/*vcf
-					do
-						sample_a=$(echo $a | cut -f7 -d_)
-						sample_b=$(echo $b | cut -f7 -d_)
-						sample_c=$(echo $c | cut -f7 -d_)
-						sample_d=$(echo $d | cut -f7 -d_)
-						rep_a=$(echo $a | cut -f8 -d_)
-						rep_b=$(echo $b | cut -f8 -d_)
-						rep_c=$(echo $c | cut -f8 -d_)
-						rep_d=$(echo $d | cut -f8 -d_)
-						if [ $sample_a == "LCL5" ] && [ $sample_b == "LCL6" ] && [ $sample_c == "LCL7" ] && [ $sample_d == "LCL8" ] && [ $rep_a == $rep_b ] && [ $rep_c == $rep_d ] && [ $rep_b == $rep_c ];then
-							cat $a | grep -v '#' > LCL5.body
-							cat $b | grep -v '#' | cut -f 10 > LCL6.body
-							cat $c | grep -v '#' | cut -f 10 > LCL7.body
-							cat $d | grep -v '#' | cut -f 10 > LCL8.body
-							echo -e "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tLCL5\tLCL6\tLCL7\tLCL8" > header_name
-							cat $a | grep '##' | cat - header_name > header
-							paste LCL5.body LCL6.body LCL7.body LCL8.body > family.body
-							cat header family.body > ${project}.$rep_a.family.vcf
-						fi
-					done
-				done
-			done
-		done
+		opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfannotate --relabel=${rename} -i ${LCL6_vcf_gz} -o LCL6.vcf.gz
+
+		opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfannotate --relabel=${rename} -i ${LCL7_vcf_gz} -o LCL7.vcf.gz
+
+		opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfannotate --relabel=${rename} -i ${LCL8_vcf_gz} -o LCL8.vcf.gz
+
+		opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg vcfmerge --force-merge-all -o ${project}.family.vcf.gz LCL5_vcf_gz LCL6_vcf_gz LCL7_vcf_gz LCL8_vcf_gz
+
+		gunzip ${project}.family.vcf.gz 
 
 	>>>
 
 		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
 	}
 	output {
-		Array[File] family_vcf = glob("*.family.vcf")
+		File merged_vcf = "${project}.family.vcf"
 	}
 }
 

workflow.wdl

-import "./tasks/split_gvcf_files.wdl" as split_gvcf_files
-import "./tasks/GVCFtyper.wdl" as GVCFtyper
 import "./tasks/benchmark.wdl" as benchmark
 import "./tasks/mendelian.wdl" as mendelian
 import "./tasks/merge_mendelian.wdl" as merge_mendelian
 import "./tasks/quartet_mendelian.wdl" as quartet_mendelian
-import "./tasks/D5_D6.wdl" as D5_D6
 import "./tasks/merge_family.wdl" as merge_family
 
 
 workflow {{ project_name }} {
 
-	Array[File] gvcf
-	Array[File] gvcf_idx
+	File LCL5
+	File LCL6
+	File LCL7
+	File LCL8
 
 	String BENCHMARKdocker
 	String MENDELIANdocker
 	String DIYdocker
-	String SENTIEON_INSTALL_DIR
-	String SENTIEONdocker
 
 
 	String fasta
 	File ref_dir
 
 	File benchmarking_dir
+	File rename
 
 	String project
 
 	String BIGcluster_config
 	String SMALLcluster_config
 
-	call GVCFtyper.GVCFtyper as GVCFtyper {
+	call benchmark.benchmark as LCL5benchmark {
 		input:
+		vcf=LCL5,
+		benchmarking_dir=benchmarking_dir,
 		ref_dir=ref_dir,
-		SENTIEON_INSTALL_DIR=SENTIEON_INSTALL_DIR,
 		fasta=fasta,
-		vcf=gvcf,
-		vcf_idx=gvcf_idx,
-		project=project,
-		docker=SENTIEONdocker,
+		docker=BENCHMARKdocker,
 		cluster_config=BIGcluster_config,
-		disk_size=disk_size
+		disk_size=disk_size,
 	}
 
-	call split_gvcf_files.split_gvcf_files as split_gvcf_files {
+	call benchmark.benchmark as LCL6benchmark {
 		input:
-		merged_gvcf=GVCFtyper.merged_gvcf,
-		docker=DIYdocker,
-		project=project,
-		cluster_config=SMALLcluster_config,
-		disk_size=disk_size
+		vcf=LCL6,
+		benchmarking_dir=benchmarking_dir,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=BENCHMARKdocker,
+		cluster_config=BIGcluster_config,
+		disk_size=disk_size,
 	}
 
+	call benchmark.benchmark as LCL7benchmark {
+		input:
+		vcf=LCL7,
+		benchmarking_dir=benchmarking_dir,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=BENCHMARKdocker,
+		cluster_config=BIGcluster_config,
+		disk_size=disk_size,
+	}	
 
-	Array[File] single_gvcf = split_gvcf_files.splited_vcf
+	call benchmark.benchmark as LCL8benchmark {
+		input:
+		vcf=LCL8,
+		benchmarking_dir=benchmarking_dir,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=BENCHMARKdocker,
+		cluster_config=BIGcluster_config,
+		disk_size=disk_size,
+	}
 
-	scatter (idx in range(length(single_gvcf))) {
-		call benchmark.benchmark as benchmark {
-			input:
-			vcf=single_gvcf[idx],
-			benchmarking_dir=benchmarking_dir,
-			ref_dir=ref_dir,
-			fasta=fasta,
-			docker=BENCHMARKdocker,
-			cluster_config=BIGcluster_config,
-			disk_size=disk_size,
-		}
+	call merge_family.merge_family as merge_family {
+		input:
+		LCL5_vcf_gz=LCL5benchmark.rtg_vcf,
+		LCL5_vcf_idx=LCL5benchmark.rtg_vcf_index,
+		LCL6_vcf_gz=LCL6benchmark.rtg_vcf,
+		LCL6_vcf_idx=LCL6benchmark.rtg_vcf_index,
+		LCL7_vcf_gz=LCL7benchmark.rtg_vcf,
+		LCL7_vcf_idx=LCL7benchmark.rtg_vcf_index,
+		LCL8_vcf_gz=LCL8benchmark.rtg_vcf,
+		LCL8_vcf_idx=LCL8benchmark.rtg_vcf,
+		rename=rename,
+		project=project,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size,
+	}
 
+	call mendelian.mendelian as mendelian {
+		input:
+		family_vcf=merge_family.merged_vcf,
+		ref_dir=ref_dir,
+		fasta=fasta,
+		docker=MENDELIANdocker,
+		cluster_config=BIGcluster_config,
+		disk_size=disk_size		
 	}
 
-	Boolean sister_tag = read_boolean(split_gvcf_files.sister_tag)
-	Boolean quartet_tag = read_boolean(split_gvcf_files.quartet_tag)
-
-	if (sister_tag) {
-		call D5_D6.D5_D6 as D5_D6 {
-			input:
-			splited_vcf=split_gvcf_files.splited_vcf,
-			project=project,
-			docker=DIYdocker,
-			cluster_config=SMALLcluster_config,
-			disk_size=disk_size,
-		}
+	call merge_mendelian.merge_mendelian as merge_mendelian {
+		input:
+		D5_trio_vcf=mendelian.D5_trio_vcf,
+		D6_trio_vcf=mendelian.D6_trio_vcf,
+		family_vcf=merge_family.merged_vcf,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size
 	}
 
-	if (quartet_tag) {
-		call merge_family.merge_family as merge_family {
-			input:
-			splited_vcf=split_gvcf_files.splited_vcf,
-			project=project,
-			docker=DIYdocker,
-			cluster_config=SMALLcluster_config,
-			disk_size=disk_size,
-		}
-
-		Array[File] family_vcfs = merge_family.family_vcf
-		scatter (idx in range(length(family_vcfs))) {
-			call mendelian.mendelian as mendelian {
-				input:
-				family_vcf=family_vcfs[idx],
-				ref_dir=ref_dir,
-				fasta=fasta,
-				docker=MENDELIANdocker,
-				cluster_config=BIGcluster_config,
-				disk_size=disk_size		
-			}
-
-			call merge_mendelian.merge_mendelian as merge_mendelian {
-				input:
-				D5_trio_vcf=mendelian.D5_trio_vcf,
-				D6_trio_vcf=mendelian.D6_trio_vcf,
-				family_vcf=family_vcfs[idx],
-				docker=DIYdocker,
-				cluster_config=SMALLcluster_config,
-				disk_size=disk_size
-			}
-		}
-
-		call quartet_mendelian.quartet_mendelian as quartet_mendelian {
-			input:
-			project_mendelian_summary=merge_mendelian.project_mendelian_summary,
-			project=project,
-			docker=DIYdocker,
-			cluster_config=SMALLcluster_config,
-			disk_size=disk_size
-		}
+	call quartet_mendelian.quartet_mendelian as quartet_mendelian {
+		input:
+		project_mendelian_summary=merge_mendelian.project_mendelian_summary,
+		project=project,
+		docker=DIYdocker,
+		cluster_config=SMALLcluster_config,
+		disk_size=disk_size
 	}
 }